whitespace_encode.py

import unicodedata


def unicode_character_name(i: int) -> str:
    """Tries to get the unicode name for a given character ordinal.
    Useful for finding various quotation marks"""
    try:
        return unicodedata.name(chr(i))
    except ValueError:
        return ""


spaces = {
    unicode_character_name(i): chr(i)
    for i in range(0, 0x10FFF)
    if "space" in (name := unicode_character_name(i).lower())
    and not any((bad in name for bad in ("wordspace", "mark", "symbol", "fill")))
}

alphabet = "".join(spaces.values())


def number_to_base(n, b):
    if n == 0:
        return [0]
    digits = []
    while n:
        digits.append(int(n % b))
        n //= b
    return digits[::-1]


def encode(n):
    return "".join(alphabet[index] for index in number_to_base(n, len(alphabet)))


def decode(encoded):
    return sum(
        [
            len(alphabet) ** position * alphabet.index(char)
            for position, char in enumerate(reversed(encoded))
        ]
    )

assert decode(encode(28657))
print("spam" + encode(28657) + "bar")
#spam  bar